Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    style and tone descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙞
    0.67
    ᴀ
    0.66
     уж
    0.66
    ೋ
    0.66
    உங்கள்
    0.64
     crippling
    0.64
    Υ
    0.64
     insanely
    0.63
     dieci
    0.63
    atás
    0.63
    POSITIVE LOGITS
     indented
    0.67
     flanked
    0.66
    Xinhua
    0.65
    Pune
    0.64
     chuan
    0.64
     asserts
    0.64
     summarizing
    0.63
     chords
    0.63
     ब्राउन
    0.63
     వు
    0.63
    Act Density 2.120%

    No Known Activations